Blind-restoration-based blind separation method for permuted motion blurred images

A novel single-channel blind separation algorithm for permuted motion blurred images is proposed by using blind restoration in this paper. Both the motion direction and the length of the point spread function （PSF） are estimated by Radon transformation and extrema a detection. Using the estimated blur parameters, the permuted image is restored by performing the L-R blind restoration method. The permutation mixing matrices can be accurately estimated by classifying the ringing effect in the restored image, thereby the source images can be separated. Simulation results show a better separation efficiency for the permuted motion blurred image with various permutation operations. The proposed algorithm indicates a better performance on the robustness against Gaussian noise and lossy JPEG compression.

Numericals for total variation-based reconstruction of motion blurred images

In this paper image with horizontal motion blur, vertical motion blur and angled motion blur are considered. We construct several difference schemes to the highly nonlinear term △↓.（△↓u/√｜△↓｜^2＋β） of the total variation-based image motion deblurring problem. The large nonlinear system is linearized by fixed point iteration method. An algebraic multigrid method with Krylov subspace acceleration is used to solve the corresponding linear equations as in [7]. The algorithms can restore the image very well. We give some numerical experiments to demonstrate that our difference schemes are efficient and robust.

3D Reconstruction for Motion Blurred Images Using Deep Learning-Based Intelligent Systems

The 3D reconstruction using deep learning-based intelligent systems can provide great help for measuring an individual’s height and shape quickly and accurately through 2D motion-blurred images.Generally,during the acquisition of images in real-time,motion blur,caused by camera shaking or human motion,appears.Deep learning-based intelligent control applied in vision can help us solve the problem.To this end,we propose a 3D reconstruction method for motion-blurred images using deep learning.First,we develop a BF-WGAN algorithm that combines the bilateral filtering(BF)denoising theory with a Wasserstein generative adversarial network(WGAN)to remove motion blur.The bilateral filter denoising algorithm is used to remove the noise and to retain the details of the blurred image.Then,the blurred image and the corresponding sharp image are input into the WGAN.This algorithm distinguishes the motion-blurred image from the corresponding sharp image according to the WGAN loss and perceptual loss functions.Next,we use the deblurred images generated by the BFWGAN algorithm for 3D reconstruction.We propose a threshold optimization random sample consensus(TO-RANSAC)algorithm that can remove the wrong relationship between two views in the 3D reconstructed model relatively accurately.Compared with the traditional RANSAC algorithm,the TO-RANSAC algorithm can adjust the threshold adaptively,which improves the accuracy of the 3D reconstruction results.The experimental results show that our BF-WGAN algorithm has a better deblurring effect and higher efficiency than do other representative algorithms.In addition,the TO-RANSAC algorithm yields a calculation accuracy considerably higher than that of the traditional RANSAC algorithm.

Parameter Estimation for Blur Image Combining Defocus and Motion Blur using Cepstrum Analysis

The degraded parameters recognition is very important for the restoration of blurred images. There are two common types of blurs for most camera systems. One is the defocus blur due to the optical system's defocus phenomenon and the other is the motion blur due to the relative movement between the objectives and the camera. Compared with the recognition for the blurred image with only one blur model, the parameter estimation for the picture combining defocus and motion blur models is a more complicated mission. A method was proposed for computer to estimate the parameters of defocus blur and motion blur in cepstrum area simultaneously. According to characters of both blur models in the frequency domain, an adjustment approach was suggested in the frequency area and then convert to the cepstrum field to increase the accuracy of measurement.

Camera Independent Motion Deblurring in Videos Using Machine Learning

In this paper, we will be looking at our efforts to find a novel solution for motion deblurring in videos. In addition, our solution has the requirement of being camera-independent. This means that the solution is fully implemented in software and is not aware of any of the characteristics of the camera. We found a solution by implementing a Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) hybrid model. Our CNN-LSTM is able to deblur video without any knowledge of the camera hardware. This allows it to be implemented on any system that allows the camera to be swapped out with any camera model with any physical characteristics.

Radon transform-based motion blurred silkworm pupa image restoration

As for machine vision-based intelligent system in the application of discriminating and sorting the sex of silkworm pupae,the tail gonad was the unique physiological feature.However,motion blur,resulting from the live silkworm pupa’s writhing motion at the moment of capturing image,could lose textures and structures(such as edge and tail gonad etc.)dramatically,which casted great challenges for sex identification.To increase the image quality and relieve the difficulty of discrimination caused by motion blur,an effective approach that including three stages was proposed in this work.In the image prediction stage,first sharp edges were acquired by using filtering techniques.Then the initial blur kernel was computed with Gaussian prior.The coarse version latent image was deconvoluted in the Fourier domain.In the kernel refinement stage,the Radon transform was applied to estimate the accurate kernel.In the final restoration step,a TV-L1 deconvolution model was carried out to obtain a better result.The experimental results showed that benefiting from the prediction step and kernel refinement step,the kernel was more accurate and the recovered image contained much more textures.It revealed that the proposed method was useful in removing the motion blur.Furthermore,the method could also be applied to other fields.

Restoration of space-variant blurred image based on motion-blurred target segmentation

In imaging on moving target, it is easy to get space- variant blurred image. In order to recover the image and gain recognizable target, an approach to recover the space-variant blurred image is presented based on image segmentation. Be- cause of motion blur＇s convolution process, the pixels of observed image＇s target and background will be displaced and piled up to produce two superposition regions. As a result, the neighbor- ing pixels in the superposition regions will have similar grey level change. According to the pixel＇s motion-blur character, the target＇s blurred edge of superposition region could be detected. Canny operator can be recurred to detect the target edge which parallels the motion blur direction. Then in the segmentation process, the whole target image which has the character of integral convolution between motion blur and real target image can be obtained. At last, the target image is restored by deconvolution algorithms with adding zeros. The restoration result indicates that the approach can effectively solve the kind of problem of space-variant motion blurred image restoration.

New Explorations on Cannon's Contributions and Generalized Solutions for Uniform Linear Motion Blur Identification

Existing frequency-domain-oriented methods of parameter identification for uniform linear motion blur （ULMB） images usually dealt with special scenarios. For example, blur-kernel directions were horizontal or vertical, or degraded images were of foursquare dimension. This excludes those identification methods from being applied to real images, especially to estimate undersized or oversized blur kernels. Pointing against the limitations of blur-kernel identifications, discrete Fourier transform （DFT）-based blur-kernel estimation methods are proposed in this paper. We analyze in depth the Fourier frequency response of generalized ULMB kernels, demonstrate in detail its related phase form and properties thereof, and put forward the concept of quasi-cepstrum. On this basis, methods of estimating ULMB-kernel parameters using amplitude spectrum and quasi-cepstrum are presented, respectively. The quasi-cepstrum-oriented approach increases the identifiable blur-kernel length, up to a maximum of half the diagonal length of the image. Meanwhile, directing toward the image of undersized ULMB, an improved method based on quasi-cepstrum is presented, which ameliorates the identification quality of undersized ULMB kernels. The quasi-cepstrum-oriented approach popularizes and applies the simulation-experiment- focused DFT theory to the estimation of real ULMB images. Compared against the amplitude-spectrum-oriented method, the quasi-cepstrum-oriented approach is more convenient and robust, with lower identification errors and of better noiseimmunity.

基于改进维纳滤波算法的运动模糊二维码图像复原方法

针对二维码在动态工业产品检测中,容易发生运动模糊,导致识别难度加大的问题,设计了一种基于改进维纳滤波的运动模糊二维码图像复原方法。在传统的维纳滤波图像复原过程中,由于正则项K值的影响,导致复原效果存在差异,结合了遗传算法,通过自适应寻优的方法实现了K值的估计,完成了图像的复原。实验结果表明:改进算法比传统算法复原以后的图像峰值信噪比(PSNR)提高了约4 dB左右,该方法可以有效地还原出运动模糊二维码图像,提高了二维码的识别的效率。

基于运动偏移信息估计的图像去运动模糊算法

针对现有动态场景图像去运动模糊算法难以有效复原非均匀复合运动模糊的问题,通过引入相机曝光轨迹来表示模糊图像中包含的运动信息,并据此提出了一种新的运动偏移估计框架,用于对潜在清晰图像在多个离散时间点的像素运动偏移进行建模。结合估计出的运动偏移信息,提出了一种融合像素运动偏移信息的多尺度单幅图像去模糊网络框架。该框架通过可变形卷积在解码阶段对运动偏移信息进行融合,给定每一像素点不同的运动约束。经过网络的多尺度编解码结构,得到每一尺度上每一像素点的预测值,实现了端对端的模糊图像复原。在GoPro和HIDE数据集上的实验结果表明,该算法能有效改善图像质量,峰值信噪比平均提升1.9 dB,结构相似度平均提升0.03。

基于光线重排的印制电路板高速扫描成像迭代去模糊方法研究

自动光学检测(automated optical inspection,AOI)相机运动速度过高,拍摄印制电路板(printed circuit board,PCB)图像会产生严重模糊。如能正确恢复因此而产生的退化,可提高相机的运动速度,进而提高AOI的检测效率。受代数迭代重建算法(algebraic reconstruction technique,ART)启发,提出一种基于光线重排的图像非盲去模糊算法。该方法在模糊核已知的情况下,基于快速迭代收缩阈值算法(fast iterative shrinkage thresholding algorithm,FISTA)迭代重建算法,运用Nestrov加速和光线重排提高了迭代收敛速度,运用数据正则抑制图像的各类加性噪声和伪影,较好地重建出原本的清晰图像。结果表明,该方法对噪声具有较好的抑制能力,对AOI相机运动曝光引起的严重模糊,较常用的传统逆滤波方法具有更好的图像恢复效果。

基于改进PSF估计的车载复杂图像复原

针对车载视频图像中同时包含局部运动模糊和全局运动模糊,现有去模糊算法难以适用且效果差等问题,提出一种基于再模糊理论的复杂车载模糊图像复原方法。根据车载视频图像的特点把图像分割为车身和非车身区域,采用改进后的模糊参数估计算法,在车身区域图像块估算出的全局运动模糊参数,对整幅图像进行全局模糊恢复;对复原前后的非车身图像进行分块处理,利用复原前后图像块结构相似度(Structural Similarity,SSIM)和局部均方差的差异性,检测和提取出局部模糊区域;对提取的模糊区域进行复原后与清晰区域拼接融合,合成清晰的图像。与现有算法对比实验分析,所提算法取得了不错的效果,且复原后图像的峰值信噪比(Peak Signal to Noise Ratio,PSNR)和SSIM表现良好。

一种基于生成对抗网络的人脸运动模糊去除方法

拍摄人像时,由于摄影器材震动或人物移动等原因,图像会出现运动模糊情况,严重影响了画面品质。而在影像跟踪或门禁识别等场景中,若画面出现运动模糊,可能导致目标无法识别,使得定位、辨认、追踪等任务失败。因此,去除运动模糊对于人脸识别应用有着至关重要的作用。文章针对人脸图像的运动模糊问题,提出一种基于生成对抗网络的人脸运动模糊去除方法,在编解码结构中引入多个跳跃连接,将卷积过程中提取的特征引入反卷积过程,同时通过全局跳跃连接,提高对特征信息的复用,并降低学习复杂度,最后调整损失函数权重,得到模糊图像到修复图像的端到端网络。实验结果表明,该方法在消除人脸运动模糊方面有较好的效果,对人脸的轮廓等细节的恢复也有很好的改善作用。

MEASUREMENT OF ANGULAR VIBRATION AMPLITUDE BY ACTIVELY BLURRED IMAGES

A novel motion-blur-based method for measuring the angular amplitude of a high-frequency rotational vibration is schemed. The proposed approach combines the active vision concept and the mechanism of motion-from-blur, generates motion blur on the image plane actively by extending exposure time, and utilizes the motion blur information in polar images to estimate the angular amplitude of a high-frequency rotational vibration. This method obtains the analytical results of the angular vibration amplitude from the geometric moments of a motion blurred polar image and an unblurred image for reference. Experimental results are provided to validate the presented scheme.

基于YOLOv8模型和LSD算法的列车接触网腕臂识别

针对列车接触网腕臂视觉检测中存在识别精度低、速度慢及腕臂图像易模糊的问题,设计了一种基于YOLOv8模型与LSD算法的接触网腕臂检测系统。首先,引入了YOLOv8目标检测模型,搭建了一种用于检测列车腕臂位置的视觉检测平台;其次,基于HIS颜色空间和图像滤波技术,对图像进行了增强处理,提升了腕臂识别的准确度;然后,基于LSD算法,完成了对接触网腕臂线段信息的提取;最后,根据现场采集的列车接触网图像,对算法的有效性进行了腕臂正反架识别实验验证。

消除或减轻CBCT常见伪影的可行化探讨与研究

随着锥形束计算机断层成像(CBCT)在医学影像领域的广泛应用,其伪影问题日益引起关注。伪影对CBCT图像的质量和诊断准确性产生不利影响,因此寻求有效的方法消除或减轻伪影对于提高CBCT影像质量具有重要意义。本文简要介绍了锥形束CT的工作原理和常见伪影类型,针对每种伪影类型,分析了其产生机制和影响因素,同时提出消除或减轻CBCT常见伪影的可行方法,提出未来的研究应致力于深入理解伪影的形成机制,开发更加精确有效的消除或减轻伪影的方法。旨在为优化CBCT图像质量,提高临床应用时的影像诊断准确性和可靠性提供参考。

基于DeblurGAN的运动模糊图像盲复原算法研究

DeblurGAN方法利用条件生成对抗网络解决了端到端的图像去模糊问题,但存在图像边缘细节恢复不足以及鲁棒性不高的问题,针对此问题,提出一种基于DeblurGAN的运动模糊图像盲复原方法。在生成网络中,采用多尺度卷积核神经网络提取特征,并使用级联空洞卷积扩大神经元的感受野;采用自适配归一化方法代替原来生成器中使用的实例归一化方法。其次,引入了梯度图像L1损失,结合对抗损失和感知损失,将其作为图像去模糊的正则约束,使得生成图像的边缘特征更加清晰。实验结果表明,提出方法复原的图像峰值信噪比数值较DeblurGAN算法高出5.4%,结构相似性指标高出1%;在主观上清晰化效果较好,且消除了网格效应。

基于事件相机的连续光流估计

事件相机对场景的亮度变化进行成像,输出异步事件流,具有极低的延时,受运动模糊问题影响较少.因此,可以利用事件相机解决高速运动场景下的光流(Optical flow,OF)估计问题.基于亮度恒定假设和事件产生模型,利用事件相机输出事件流的低延时性质,融合存在运动模糊的亮度图像帧,提出基于事件相机的连续光流估计算法,提升了高速运动场景下的光流估计精度.实验结果表明,相比于现有的基于事件相机的光流估计算法,该算法在平均端点误差、平均角度误差和均方误差3个指标上,分别提升11%、45%和8%.在高速运动场景下,该算法能够准确重建出高速运动目标的连续光流,保证了存在运动模糊情况时,光流估计的精度.

高速飞行条件下长曝光图像复原方法

在大气层、临界层中高速飞行的飞行器其周边的光学成像环境复杂,准确求解点扩散函数并抑制噪声是图像复原的两个重点。针对目前复原算法存在抗噪性能差、先验信息利用不足等问题,本文提出高速飞行条件下长曝光图像的图像复原方法。首先构造多尺度多方向形态学滤波器对图像进行去噪预处理;引入小波变换将小波的多分辨率特征与图像复原相结合,进一步抑制残留噪声并加快运算速度;采用结合最大类间方差法的Radon变换计算运动模糊点扩散函数;最后构造多直线拟合模型,提出基于图像梯度的对称频谱估计,自适应重建清晰图像频谱。实验表明,本文算法可使用单幅长曝光图像完成有效去噪和去模糊,满足实时复原场景,PSNR和SSIM评价指标数值有效提升。

一种基于图像形态学的深空图像模糊复原方法

针对深空目标与空间相机相对运动造成的图像运动模糊问题,文章提出了一种基于图像形态学的运动模糊复原方法。首先运用图像形态学细化的方法消除图像中的冗余信息,快速提取图像中目标的特征;其次运用最小二乘法直线拟合方法对目标运动方向进行估计,再利用连通域划分结果对目标运动长度进行估计;最后采用约束最小二乘方滤波对退化模型进行逆推导运算来实现目标运动模糊复原。通过实验验证结果表明:文章提出的基于图像形态学的深空图像运动模糊复原方法能够正确估计运动模型参数,通用性强,易于在轨实现,可以处理目标与相机相对运动造成的运动模糊问题,在目标运动方向不一致的图像中取得了良好的复原效果。